Implementation of Talairach Atlas Based Automated Brain Segmentation for Radiation Therapy Dosimetry

A Monte Carlo simulation-based decision support system for radiation oncologists in the treatment of glioblastoma multiforme

In the present research, we have developed a model-based crisp logic function statistical classifier decision support system supplemented with treatment planning systems for radiation oncologists in the treatment of glioblastoma multiforme (GBM). This system is based on Monte Carlo radiation transport simulation and it recreates visualization of treatment environments on mathematical anthropomorphic brain (MAB) phantoms. Energy deposition within tumour tissue and normal tissues are graded by quality audit factors which ensure planned dose delivery to tumour site thereby minimising damages to healthy tissues. The proposed novel methodology predicts tumour growth response to radiation therapy from a patient-specific medicine quality audit perspective. Validation of the study was achieved by recreating thirty-eight patient-specific mathematical anthropomorphic brain phantoms of treatment environments by taking into consideration density variation and composition of brain tissues. Dose computations accomplished through water phantom, tissue-equivalent head phantoms are neither cost-effective, nor patient-specific customized and is often less accurate. The above-highlighted drawbacks can be overcome by using open-source Electron Gamma Shower (EGSnrc) software and clinical case reports for MAB phantom synthesis which would result in accurate dosimetry with due consideration to the time factors. Considerable dose deviations occur at the tumour site for environments with intraventricular glioblastoma, haematoma, abscess, trapped air and cranial flaps leading to quality factors with a lower logic value of 0. Logic value of 1 depicts higher dose deposition within healthy tissues and also leptomeninges for majority of the environments which results in radiation-induced laceration.

Automatic Segmentation with Deep Learning in Radiotherapy

This review provides a formal overview of current automatic segmentation studies that use deep learning in radiotherapy. It covers 807 published papers and includes multiple cancer sites, image types (CT/MRI/PET), and segmentation methods. We collect key statistics about the papers to uncover commonalities, trends, and methods, and identify areas where more research might be needed. Moreover, we analyzed the corpus by posing explicit questions aimed at providing high-quality and actionable insights, including: "What should researchers think about when starting a segmentation study?", "How can research practices in medical image segmentation be improved?", "What is missing from the current corpus?", and more. This allowed us to provide practical guidelines on how to conduct a good segmentation study in today's competitive environment that will be useful for future research within the field, regardless of the specific radiotherapeutic subfield. To aid in our analysis, we used the large language model ChatGPT to condense information.

SPARSE: Seed Point Auto-Generation for Random Walks Segmentation Enhancement in medical inhomogeneous targets delineation of morphological MR and CT images

In medical image processing, robust segmentation of inhomogeneous targets is a challenging problem. Because of the complexity and diversity in medical images, the commonly used semiautomatic segmentation algorithms usually fail in the segmentation of inhomogeneous objects. In this study, we propose a novel algorithm imbedded with a seed point autogeneration for random walks segmentation enhancement, namely SPARSE, for better segmentation of inhomogeneous objects. With a few user-labeled points, SPARSE is able to generate extended seed points by estimating the probability of each voxel with respect to the labels. The random walks algorithm is then applied upon the extended seed points to achieve improved segmentation result. SPARSE is implemented under the compute unified device architecture (CUDA) programming environment on graphic processing unit (GPU) hardware platform. Quantitative evaluations are performed using clinical homogeneous and inhomogeneous cases. It is found that the SPARSE can greatly decrease the sensitiveness to initial seed points in terms of location and quantity, as well as the freedom of selecting parameters in edge weighting function. The evaluation results of SPARSE also demonstrate substantial improvements in accuracy and robustness to inhomogeneous target segmentation over the original random walks algorithm.

Longitudinal rates of lobar atrophy in frontotemporal dementia, semantic dementia, and Alzheimer's disease

This study compared rates of regional atrophy in Alzheimer disease (AD), frontotemporal dementia (FTD), and semantic dementia (SD). Cross-sectional studies have shown that different dementia syndromes are associated with different patterns of regional brain tissue loss. Rates of atrophy over time may be useful for differential diagnosis, and could be used to monitor disease progression, serving as an outcome measure for clinical trials. We studied patients with AD (n=12), FTD (n=13), SD (n=20), and normal controls (n=23) longitudinally with structural magnetic resonance imaging, using BRAINS2 software to measure frontal, temporal, and parietal lobe volumes. In FTD the rate of frontal lobe atrophy over 1 year was greater than in any other group, whereas SD showed the highest rate in the temporal lobes. Atrophy in these regions progressed twice as quickly in FTD and SD compared with AD. Atrophy was not significantly faster for AD in any brain region compared with the other groups. Regional atrophy over time was significantly faster in FTD and SD compared with AD, and the regions of greatest atrophy were specific for each syndrome. Measuring specific regions of cerebral volume changes by serial neuroimaging may serve as a useful biomarker outcome measure for clinical trials in neurodegenerative diseases.

Quantification of spatial consistency in the Talairach and Tournoux stereotactic atlas

BACKGROUND

The Talairach-Tournoux (TT) atlas is one of the most prevalent brain atlases. Although its spatial inconsistencies were reported earlier, there has been no systematic quantification of them across the entire atlas, which is addressed here.

METHOD

The consistency of the TT atlas, defined as uniformity of labeling across all three orthogonal atlas orientations, is calculated and presented as maps. It is analyzed in function of discrepancy measuring spatial offset in labeling.

FINDINGS

The TT atlas has 27.4% consistency and 37.7% inconsistency. The most consistent structure is the thalamus (85.7% consistency, 5.4% inconsistency). The consistency of the basal ganglia is good. For 3-mm discrepancy, the inconsistency of major subcortical gray matter structures is very low: 0% (globus pallidus medial and putamen), 0.7% (thalamus), 2.2% (globus pallidus lateral), 4.8% (hippocampus) and 4.9% (caudate nucleus). The inconsistency of all subcortical structures is relatively high (16.8%), caused by a very high inconsistency of white matter tracts. The consistency of stereotactic targets is 69.2% (GPi), 50.0% (STN) and 42.9% (VPL). The overall TT consistency increases by 20% for 1-mm discrepancy, constantly grows by 10% for 2-4-mm discrepancy and slows down to 3% for 5-6-mm discrepancy.

CONCLUSION

This work enhances our understanding of the TT atlas and its variable spatial consistency. It is helpful in using multiple atlas orientations simultaneously. It also may be useful in atlas interpolation and construction of a fully consistent 3D atlas. As the consistency of the main stereotactic targets is medium, the use of the TT atlas in stereotactic procedures requires a great deal of care and understanding of its limitations.

A pre-clinical assessment of an atlas-based automatic segmentation tool for the head and neck

BACKGROUND AND PURPOSE

Accurate conformal radiotherapy treatment requires manual delineation of target volumes and organs at risk (OAR) that is both time-consuming and subject to large inter-user variability. One solution is atlas-based automatic segmentation (ABAS) where a priori information is used to delineate various organs of interest. The aim of the present study is to establish the accuracy of one such tool for the head and neck (H&N) using two different evaluation methods.

MATERIALS AND METHODS

Two radiotherapy centres were provided with an ABAS tool that was used to outline the brainstem, parotids and mandible on several patients. The results were compared to manual delineations for the first centre (EM1) and reviewed/edited for the second centre (EM2), both of which were deemed as equally valid gold standards. The contours were compared in terms of their volume, sensitivity and specificity with the results being interpreted using the Dice similarity coefficient and a receiver operator characteristic (ROC) curve.

RESULTS

Automatic segmentation took typically approximately 7min for each patient on a standard PC. The results indicated that the atlas contour volume was generally within +/-1SD of each gold standard apart from the parotids for EM1 and brainstem for EM2 that were over- and under-estimated, respectively (within +/-2SD). The similarity of the atlas contours with their respective gold standard was satisfactory with an average Dice coefficient for all OAR of 0.68+/-0.25 for EM1 and 0.82+/-0.13 for EM2. All data had satisfactory sensitivity and specificity resulting in a favourable position in ROC space.

CONCLUSIONS

These tests have shown that the ABAS tool exhibits satisfactory sensitivity and specificity for the OAR investigated. There is, however, a systematic over-segmentation of the parotids (EM1) and under-segmentation of the brainstem (EM2) that require careful review and editing in the majority of cases. Such issues have been discussed with the software manufacturer and a revised version is due for release.

Evaluation of an atlas-based automatic segmentation software for the delineation of brain organs at risk in a radiation therapy clinical context

BACKGROUND AND PURPOSE

Conformal radiation therapy techniques require the delineation of volumes of interest, a time-consuming and operator-dependent task. In this work, we aimed to evaluate the potential interest of an atlas-based automatic segmentation software (ABAS) of brain organs at risk (OAR), when used under our clinical conditions.

MATERIALS AND METHODS

Automatic and manual segmentations of the eyes, optic nerves, optic chiasm, pituitary gland, brain stem and cerebellum of 11 patients on T1-weighted magnetic resonance, 3-mm thick slice images were compared using the Dice similarity coefficient (DSC). The sensitivity and specificity of the ABAS were also computed and analysed from a radiotherapy point of view by splitting the ROC (Receiver Operating Characteristic) space into four sub-regions.

RESULTS

Automatic segmentation of OAR was achieved in 7-8 min. Excellent agreement was obtained between automatic and manual delineations for organs exceeding 7 cm3: the DSC was greater than 0.8. For smaller structures, the DSC was lower than 0.41.

CONCLUSIONS

These tests demonstrated that this ABAS is a robust and reliable tool for automatic delineation of large structures under clinical conditions in our daily practice, even though the small structures must continue to be delineated manually by an expert.